Back

Speaker "Peter Lenz" Details Back

 

Topic

From latitude & longitude to decision making in 15ms

Abstract

Dstillery has to make complex machine-learning-based decisions on a quarter trillion events every day, in real time. This talk will explore one aspect of that decision making process: geospatial. We'll follow one event through our stack, stopping at each geo-related process and discuss what that process does, why we do it, how we make it fast, and finally what we do with all that data in the end.

Profile

Peter Lenz is a geographer and data scientist with Dstillery, a data insights company that builds behavioral profiles from billions of observations of human behavior every day using machine learning. Specializing in geographic big data and data storytelling, Peter can dive anywhere into the data pipeline from writing code, training models, to discovering insights in the data. He built up skill set working in the urban planning world, first at a consulting firm and later with an agency of the Department of the Interior. A native of New York City, today he and his family live in the Hudson Valley.